E‐Shape Analysis Page: 16
View a full description of this thesis.
Extracted Text
The following text was automatically extracted from the image on this page using optical character recognition software:
classified with 100% accuracy and no false positives. The other two senders were from real
human conversations.
This method reveals a very powerful tool in categorizing incoming emails when comparing
non-human to human emails. Newsletters, advertisements, and solicitations can be moved
separately by themselves to be reviewed later by a user, keeping priority emails displayed first.
2.5. Limitations of the Study
Currently the E-shape analysis tool does not have a way to compliment its decision process
by removing email threads and conversations. This drawback is reduced by the power of E-
shape analysis, but it believed that I still yet have many abilities to unlock in this regard.
The shape analysis is a very useful tool to complement other tools as it can provide
the deciding factor to many close decisions. Such is the example in spam detection where
the content classifier can already achieve such a high accuracy. Some emails are short by
nature, the ability for shape analysis to distinguish between others becomes limited. In the
case of spam, short emails are common and the limitation impact of E-shape analysis will be
mitigated to a large extent.
As mentioned earlier, and with any tool, the less information you give it, the less it
can tell you. In the study of social context-based finger print detection, if a subject has a
subset of friends that like to send web hyperlinks back and forth, the classifier will be unable
to distinguish between users. Study of group based social awareness could be a possible
application of this research.
Botnet detection is a challenging problem. There is not a singular solution to this threat,
and combining the latest innovations only brings us a step closer. The purpose of E-shape
analysis for botnets is to bring the world one step closer. E-shape analysis is a tool capable
of template/campaign identification to find a spamming bots before they are even able to
send. Botnet identification is the next logical step of the process and can be supported with
this tool.16
Upcoming Pages
Here’s what’s next.
Search Inside
This thesis can be searched. Note: Results may vary based on the legibility of text within the document.
Tools / Downloads
Get a copy of this page or view the extracted text.
Citing and Sharing
Basic information for referencing this web page. We also provide extended guidance on usage rights, references, copying or embedding.
Reference the current page of this Thesis.
Sroufe, Paul. E‐Shape Analysis, thesis, December 2009; Denton, Texas. (https://digital.library.unt.edu/ark:/67531/metadc12201/m1/25/: accessed July 17, 2024), University of North Texas Libraries, UNT Digital Library, https://digital.library.unt.edu; .